Hardware
How to Use AI Agents to Prepare 3D Scenes for Simulation
Agentic AI workflows using NVIDIA Omniverse libraries automate preparation of Blender scenes for robotics simulation by adding semantic labels, sensor definitions, physics properties and validating th
Agentic AI workflows using NVIDIA Omniverse libraries automate preparation of Blender scenes for robotics simulation by adding semantic labels, sensor definitions, physics properties and validating them. Codex or Claude coordinates the overall process while NemoClaw deploys Hermes sub‑agents that author physics with ovphysx, render preflight views with ovrtx, and run SimReady validation against target profiles, all over a shared OpenUSD contract layer that preserves hierarchy and metadata for iterative edits. The resulting simulation‑ready USD package is handed off to Isaac Sim or Isaac Lab after passing the acceptance gate.
Related
- Integrate NVIDIA Omniverse RTX Sensor Simulation Into Existing Apps
- Integrate Physical AI Capabilities into Existing Apps with NVIDIA Omniverse Libraries
- Develop Lightweight USD Runtimes Faster with AI Agents
Source: NVIDIA Developer | 2026-09-16